Abstract A025: Real-World Data–Driven Target Discovery in Advanced NSCLC

Abstract

Real-world data (RWD) is increasingly leveraged to inform clinical development and health-outcomes research in oncology; however, its use in therapeutic target identification (Target ID) remains underexplored. Emerging non-invasive liquid biopsy technologies now enable large-scale, longitudinal molecular profiling within routine care, offering a unique opportunity to derive biologically rich, clinically grounded insights at population scale. We assessed whether multimodal RWD—including blood-based genomic and epigenomic NGS—combined with machine learning (ML) could generate actionable Target ID hypotheses in advanced non–small cell lung cancer (NSCLC). We analyzed a de-identified cohort of several hundred patients with advanced NSCLC from Guardant's InfinityAI Data Library, a multimodal oncology real-world data platform integrating longitudinal clinical records, treatment histories, outcomes, and liquid biopsy–derived genomic and epigenomic profiles. The analysis followed a two-phase framework. Phase 1 used baseline, pre-treatment liquid biopsy data to identify molecular features and pathway-level programs associated with primary resistance, defined using real-world response metrics including time-to-discontinuation and time-to-next-treatment. Phase 2 extends this framework to longitudinal post-treatment profiling to characterize treatment-induced molecular changes and emergent dependencies. Machine learning–derived candidates are prioritized using literature review, ClinicalTrials.gov, patent analysis, and public functional datasets (TCGA, DepMap). ML analysis revealed reproducible molecular signals and pathways associated with divergent clinical outcomes, including features extending beyond canonical oncogenic drivers. Incorporation of epigenomic RWD substantially improved predictive performance and provided mechanistic insight not captured by genomic alterations alone. The prioritized targets recapitulated known resistance mechanisms while uncovering previously unrecognized, potentially actionable pathways implicated in treatment resistance and disease progression. This work demonstrates the novel application and value of multimodal liquid-biopsy RWD for scalable, clinically anchored therapeutic Target ID in solid tumors. Integrating real-world molecular and clinical data with ML offers a complementary discovery paradigm that accelerates hypothesis generation grounded in patient outcomes. Ongoing in vitro studies across diverse cancer cell lines will further interrogate prioritized targets and support translation toward therapeutic development. Aaron Hardin, Peili Zhang, Amar Das. Real-World Data–Driven Target Discovery in Advanced NSCLC [abstract]. In: Proceedings of AACR Drug Discovery and Development (AACR D3) Conference; 2026 Jul 21-24; Boston, MA. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(14_Suppl):Abstract nr A025.